Comparative Study of AI-Based Video Optimization Techniques: Super-Resolution, Denoising, and Frame Interpolation
Journal of Technology and Data Science · 31.12.2024 · 2 (2) · 21-32
DOI: 10.59025/ab894b41 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Technology and Data Science, online erschienen am 31.12.2024. Verfasst von Untoro Apsiswanto und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Video quality degradation due to low resolution, noise, and limited frame rate poses a significant challenge in modern digital content ecosystems, ranging from streaming services to real-time surveillance systems. This study presents a systematic comparative analysis of three categories of artificial intelligence-based video optimization techniques—super-resolution, denoising, and frame interpolation—benchmarked against conventional methods through simulation on five representative video test clips. Six state-of-the-art deep learning models were evaluated using four quantitative metrics: PSNR, SSIM, LPIPS, and VMAF. Results demonstrate that AI-based methods consistently outperform conventional approaches, with VRT achieving optimal performance in super-resolution (PSNR 34.2 dB) and RIFE attaining the best frame interpolation score (SSIM 0.941).
Zitieren
APA
Apsiswanto, U., & Yusuf, R. (2024). Comparative Study of AI-Based Video Optimization Techniques: Super-Resolution, Denoising, and Frame Interpolation. Journal of Technology and Data Science, 2(2), 21-32. https://doi.org/10.59025/ab894b41
Vancouver
Apsiswanto U, Yusuf R. Comparative Study of AI-Based Video Optimization Techniques: Super-Resolution, Denoising, and Frame Interpolation. Journal of Technology and Data Science. 2024;2(2):21-32. doi:10.59025/ab894b41
BibTeX
@article{Apsiswanto2024,
author = {Apsiswanto, Untoro and Yusuf, Ridwan},
title = {Comparative Study of AI-Based Video Optimization Techniques: Super-Resolution, Denoising, and Frame Interpolation},
journal = {Journal of Technology and Data Science},
year = {2024},
volume = {2},
number = {2},
pages = {21--32},
doi = {10.59025/ab894b41}
}
EUVIMED